mirror of
https://github.com/QwenLM/qwen-code.git
synced 2026-07-09 17:19:02 +00:00
9605bcc25f
* feat(cua-driver): sync vendored cua-driver from 0.6.8 to 0.7.0 Upstream 0.7.0 brings action-time modality (get_window_state always returns AX tree + screenshot, capture_mode retired), honest verification (every action returns verified/path/effect/escalation), browser page (CDP) tools, desktop-scope (capture_scope=window|desktop, get_desktop_state, screen-absolute click/scroll), and Rust-only consolidation (Swift backend retired). Cherry-pick patch changes: - #2025 (X11 synthetic click): retired — superseded by 0.7.0 honest-verification - #2035 (session revive): retired — superseded by 0.7.0 revive_session/loud-reject/is_session_lifecycle_tool - #2036 (EAGAIN socket write retry): re-injected — merged upstream post-0.7.0 tag, EAGAIN os error 35 is not acceptable - #2021 (null/empty-title windows + resolve_uwp_host_window): retained, adapted to 0.7.0's new is_listable_top_level and window_title helpers Shim extensions: - coord_norm: desktop-scope support — denormalize_args falls back to screen basis when no window cache (desktop-scope click), normalize_result handles get_desktop_state, ingest_screen_size reads get_desktop_state's screen_width/height - serve.rs: rewrite_coord_desc re-injected at both tools/list sites Install scripts simplified to Rust-only (Swift backend retired upstream). Fix platform-linux cross-compilation: cfg-gate wayland::PORTAL_LIBEI_ENABLED reference in health_report.rs for non-linux hosts. * fix(cua-driver): distinguish desktop-scope from window cache miss in denormalize_args When screenshot_w == 0 (no cached window size), check whether the call has a pid/window_id target before falling back to screen-size basis. Window-scoped clicks with a cache miss now correctly leave coordinates as-is instead of mapping them against the screen dimensions. * fix(cua-driver): use screenshot pixels not logical points for desktop-scope coord basis ingest_screen_size was reading screen_width/height (logical display points from CGDisplayBounds) for get_desktop_state, but the model operates on the screenshot PNG whose dimensions are physical pixels. On Retina displays (2x) this caused every desktop-scope click to land at half the intended position. Read screenshot_width/height instead — the same basis normalize_result rewrites to 1000. Updated test to use realistic Retina values (screen 1920, screenshot 3840) to catch 1:1 masking. * fix(cua-driver): split screen cache into logical (move_cursor) and physical (desktop-scope) The single screen_cache was being written by both get_screen_size (logical points, e.g. 1920x1080) and get_desktop_state (physical pixels, e.g. 3840x2160). Since move_cursor operates in CGEvent screen points (logical) while desktop-scope clicks operate in screenshot pixels (physical), whichever tool ran last would corrupt the other's denormalization basis — causing 2x overshoot or 1/2 offset on Retina. Split into: - SCREEN_SIZE: logical points, written by get_screen_size, consumed by move_cursor (screen_basis=true) - DESKTOP_SCREENSHOT_SIZE: physical pixels, written by get_desktop_state, consumed by desktop-scope click fallback (screenshot_w==0, no pid) Added cross-contamination isolation tests. --------- Co-authored-by: Shaojin Wen <shaojin.wensj@alibaba-inc.com> |
||
|---|---|---|
| .github | ||
| .husky | ||
| .qwen | ||
| .vscode | ||
| docs | ||
| docs-site | ||
| eslint-rules | ||
| integration-tests | ||
| packages | ||
| patches | ||
| scripts | ||
| .dockerignore | ||
| .editorconfig | ||
| .gitattributes | ||
| .gitignore | ||
| .npmrc | ||
| .nvmrc | ||
| .prettierignore | ||
| .prettierrc.json | ||
| .yamllint.yml | ||
| AGENTS.md | ||
| CHANGELOG.md | ||
| CLAUDE.md | ||
| CONTRIBUTING.md | ||
| Dockerfile | ||
| esbuild.config.js | ||
| eslint.config.js | ||
| eslint.legacy-filenames.mjs | ||
| LICENSE | ||
| Makefile | ||
| package-lock.json | ||
| package.json | ||
| README.md | ||
| SECURITY.md | ||
| tsconfig.json | ||
| vitest.config.ts | ||
The open-source AI coding agent that lives in your terminal.
中文 | Deutsch | français | 日本語 | Русский | Português (Brasil)
Why Qwen Code?
- Agentic out of the box — Auto-Memory, Auto-Skills, SubAgents, Agent Teams, and MCP. Dynamic workflows, zero setup.
- Open-source, inside and out — The framework and the Qwen models are open-source. They evolve together. No vendor lock-in.
- Multi-protocol — Supports OpenAI, Anthropic, Gemini, and Qwen APIs. Any third-party provider or local model (Ollama / vLLM). Switch at runtime.
- Beyond the terminal — IDE plugins, Desktop app, daemon mode, SDKs, and IM bots (Telegram / DingTalk / WeChat / Feishu).
Tip
Qwen Code is actively iterating on itself — using its own agent and models to file issues, submit PRs, review code, and run tests. Powered by the community, driven by AI.
Installation
Linux / macOS:
curl -fsSL https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.sh | bash
Windows:
irm https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.ps1 | iex
Restart your terminal after installation to ensure environment variables take effect.
NPM / Homebrew
NPM (requires Node.js 22+):
npm install -g @qwen-code/qwen-code@latest
Homebrew (macOS / Linux):
brew install qwen-code
Quick Start
qwen # Launch interactive terminal UI
# Inside the session:
/auth # Configure your provider and API key
See the Authentication Guide and Settings Reference for detailed setup.
How to Use Qwen Code
| Mode | Command | Use Case |
|---|---|---|
| Interactive | qwen |
Terminal UI with rich rendering, @file references, slash commands |
| Headless | qwen -p "..." |
Scripts, CI/CD, batch processing — no UI |
| IDE | — | VS Code, Zed, JetBrains |
| Desktop | — | Qwen Code Desktop — GUI for macOS, Windows, Linux |
| Daemon | qwen serve |
Shared agent session over HTTP+SSE (ACP). Multiple clients, one agent. (experimental) Docs |
| SDK | — | TypeScript, Python, Java |
| IM Bot | qwen channel |
Connect to Telegram, DingTalk, WeChat, or Feishu |
SDK example (Python)
import asyncio
from qwen_code_sdk import is_sdk_result_message, query
async def main() -> None:
result = query(
"Summarize the repository layout.",
{
"cwd": "/path/to/project",
"path_to_qwen_executable": "qwen",
},
)
async for message in result:
if is_sdk_result_message(message):
print(message["result"])
asyncio.run(main())
Capabilities
If you know Claude Code, you already know Qwen Code — and then some. We've put significant effort into bringing Qwen Code to feature parity with Claude Code, improving both breadth and reliability across the board.
| Feature | Qwen Code | Claude Code |
|---|---|---|
| SubAgents, Agent Teams, Dynamic Workflows | ✓ | ✓ |
| Auto-Memory, Auto-Skills, Hooks | ✓ | ✓ |
| Built-in Skills (/review, /batch, /loop, /bugfix…) | ✓ | ✓ |
| MCP, Plan Mode, LSP Integration | ✓ | ✓ |
| Auto Mode, Sandbox, Git Worktrees | ✓ | ✓ |
| Computer Use (desktop automation) | ✓ | ✓ |
| IDE Plugins (VS Code / JetBrains / Zed) | ✓ | ✓ |
| SDK | ✓ | ✓ |
| Headless Mode, Session Management | ✓ | ✓ |
| Open-source — model and framework | ✓ | — |
| Multi-protocol (OpenAI / Anthropic / Gemini / Qwen + any provider) | ✓ | — |
| Agent Arena (multi-model head-to-head on same task) | ✓ | — |
Daemon Mode — qwen serve (multi-client shared agent) |
✓ | — |
| IM Channels (Telegram / DingTalk / WeChat / Feishu) | ✓ | — |
Ecosystem
-
Qwen Code Desktop — Official desktop app for macOS, Windows, and Linux
-
AionUi — A modern GUI for command-line AI tools including Qwen Code
-
Gemini CLI Desktop — A cross-platform desktop/web/mobile UI for Qwen Code
-
🦞 Qwen Code Claw — Let other agents (Claude, Codex, etc.) delegate coding tasks to Qwen Code via ACP. Paste this prompt into your agent:
Use Qwen Code as a coding agent. First, fetch and read this skill reference:
https://raw.githubusercontent.com/QwenLM/qwen-code/refs/heads/main/.qwen/skills/qwen-code-claw/SKILL.md
Then follow the instructions inside to install, authenticate, and use Qwen Code via acpx for all coding tasks.
Contributing
Contributions are welcome! See CONTRIBUTING.md for guidelines.
Acknowledgments
This project was originally based on Google Gemini CLI v0.8.2. We gratefully acknowledge the Gemini CLI team's excellent work. Starting from Qwen Code v0.1, we stopped syncing with upstream and began independent development as a multi-protocol, multi-platform agent framework with deep integrations for Qwen models and beyond.